Dismiss
The InnovationQ application will be updated on Sunday, May 31st from 10am-noon ET. You may experience brief service interruptions during that time.
Browse Prior Art Database

Using quantized probabilities to overcome the requirement of fully observed data in generic Bayesian networks structure learning algorithms

IP.com Disclosure Number: IPCOM000183826D
Original Publication Date: 2009-Jun-02
Included in the Prior Art Database: 2009-Jun-02

Publishing Venue

IBM

Abstract

This article describes a solution to overcome the problem of using soft evidence in structure learning process, using quantized probabilities to overcome the requirement of fully observed data in generic Bayesian networks structure learning algorithms .